Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    making progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ḳ
    -0.08
    ','"+
    -0.08
    Š
    -0.07
    公诉
    -0.07
    ¾
    -0.07
    IntPtr
    -0.07
    (args
    -0.07
     ---------------------------------------------------------------------------↵
    -0.07
     hind
    -0.07
    ống
    -0.07
    POSITIVE LOGITS
    encil
    0.08
    表格
    0.08
     artic
    0.07
    orting
    0.07
    _vertex
    0.07
    تحول
    0.07
    .className
    0.07
    stab
    0.07
     scor
    0.07
     Ident
    0.07
    Act Density 0.014%

    No Known Activations